get_design_violations
Scan the entire src/ directory for design governance violations. Groups results by file, sorted by severity. Supports filtering by severity (high/medium/low/all) and category (color/typography/layout/states/focus/button/all). Returns summary stats, compliance score (0-100), and top violations up ...
This record as markdown: /tools/io-github-homenshum-nodebench/get-design-violations.md
What get_design_violations does on Nodebench
AI agents call get_design_violations to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_design_violations is rated Low
This is a read-only audit and analysis tool. It queries a codebase for design violations, groups results, and generates reports. No data is created, modified, deleted, or external operations triggered. The lowest severity (low) is appropriate because the blast radius of misuse is minimal — an agent could only retrieve information about design issues, not cause harm.
From the tool's definition The tool 'scan[s] the entire src/ directory' and 'returns summary stats, compliance score, and top violations' — it retrieves and analyzes design governance data without modifying, executing external operations, or deleting anything.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs get_design_violations safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_design_violations, this is the rule to start with:
get_design_violations is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every get_design_violations call is checked against it from then on.
Questions about get_design_violations
Scan the entire src/ directory for design governance violations. Groups results by file, sorted by severity. Supports filtering by severity (high/medium/low/all) and category (color/typography/layout/states/focus/button/all). Returns summary stats, compliance score (0-100), and top violations up to the limit. Use for project-wide design audits. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for get_design_violations: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nodebench. Nothing to install.
get_design_violations is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_design_violations rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_design_violations. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_design_violations is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue